diff mbox series

[FFmpeg-devel,09/13] lavc/jpeg2000: Speed up ff_jpeg2000_tag_tree_init() using stereotypes for sizes <= 4x4

Message ID 5141c5587ce703481b716b9898e086e47f763a49.camel@acc.umu.se
State New
Headers show
Series [FFmpeg-devel,01/13] lavc/jpeg2000dec: Finer granularity threading | expand

Checks

Context Check Description
andriy/configure_x86 warning Failed to apply patch

Commit Message

Tomas Härdin June 14, 2022, 2:43 p.m. UTC

Comments

Anton Khirnov June 18, 2022, 3 p.m. UTC | #1 
Quoting Tomas Härdin (2022-06-14 16:43:38)
> 
> 
> From 03b806f89453571310dcb14edbd9f51e059b7476 Mon Sep 17 00:00:00 2001
> From: =?UTF-8?q?Tomas=20H=C3=A4rdin?= <git@haerdin.se>
> Date: Wed, 8 Jun 2022 10:08:15 +0200
> Subject: [PATCH 09/13] lavc/jpeg2000: Speed up ff_jpeg2000_tag_tree_init()
>  using stereotypes for sizes <= 4x4
> 
> ---
>  libavcodec/jpeg2000.c | 35 +++++++++++++++++++++++++++++++++++
>  1 file changed, 35 insertions(+)
> 
> diff --git a/libavcodec/jpeg2000.c b/libavcodec/jpeg2000.c
> index 0bec2e187d..b80e68bcba 100644
> --- a/libavcodec/jpeg2000.c
> +++ b/libavcodec/jpeg2000.c
> @@ -51,6 +51,31 @@ static int32_t tag_tree_size(int w, int h)
>      return (int32_t)(res + 1);
>  }
>  
> +#define T(x) (x*sizeof(Jpeg2000TgtNode))
> +
> +static const size_t tt_sizes[16] = {
> +    T(1),T(3),T(6),T(7),T(3),T(5),T(9),T(11),T(6),T(9),T(14),T(17),T(7),T(11),T(17),T(21),
> +};
> +
> +static const Jpeg2000TgtNode tt_stereotypes[16][21] = {
> +    {{-1},},
> +    {{2},{2},{-1},},
> +    {{3},{3},{4},{5},{5},{-1},},
> +    {{4},{4},{5},{5},{6},{6},{-1},},
> +    {{2},{2},{-1},},
> +    {{4},{4},{4},{4},{-1},},
> +    {{6},{6},{7},{6},{6},{7},{8},{8},{-1},},
> +    {{8},{8},{9},{9},{8},{8},{9},{9},{10},{10},{-1},},
> +    {{3},{3},{4},{5},{5},{-1},},
> +    {{6},{6},{6},{6},{7},{7},{8},{8},{-1},},
> +    {{9},{9},{10},{9},{9},{10},{11},{11},{12},{13},{13},{13},{13},{-1},},
> +    {{12},{12},{13},{13},{12},{12},{13},{13},{14},{14},{15},{15},{16},{16},{16},{16},{-1},},
> +    {{4},{4},{5},{5},{6},{6},{-1},},
> +    {{8},{8},{8},{8},{9},{9},{9},{9},{10},{10},{-1},},
> +    {{12},{12},{13},{12},{12},{13},{14},{14},{15},{14},{14},{15},{16},{16},{16},{16},{-1},},
> +    {{16},{16},{17},{17},{16},{16},{17},{17},{18},{18},{19},{19},{18},{18},{19},{19},{20},{20},{20},{20},{-1},},
> +};
> +
>  /* allocate the memory for tag tree */
>  static int ff_jpeg2000_tag_tree_init(Jpeg2000TgtNode **old, unsigned int *size, int w, int h)
>  {
> @@ -59,6 +84,15 @@ static int ff_jpeg2000_tag_tree_init(Jpeg2000TgtNode **old, unsigned int *size,
>      int32_t tt_size, ofs = 0;
>      size_t prod;
>  
> +    if (w <= 4 && h <= 4) {
> +        int idx = w-1 + (h-1)*4;
> +        size_t sz = tt_sizes[idx];
> +        av_fast_malloc(old, size, sz);

Unchecked mallocs are of the beast.
Tomas Härdin June 21, 2022, 7:57 a.m. UTC | #2 
lör 2022-06-18 klockan 17:00 +0200 skrev Anton Khirnov:
> Quoting Tomas Härdin (2022-06-14 16:43:38)
> > 
> > +    if (w <= 4 && h <= 4) {
> > +        int idx = w-1 + (h-1)*4;
> > +        size_t sz = tt_sizes[idx];
> > +        av_fast_malloc(old, size, sz);
> 
> Unchecked mallocs are of the beast.

Right, it should return AVERROR(ENOMEM) if !*old. Will be fixed in the
updated patchset

/Tomas
diff mbox series

Patch

From 03b806f89453571310dcb14edbd9f51e059b7476 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tomas=20H=C3=A4rdin?= <git@haerdin.se>
Date: Wed, 8 Jun 2022 10:08:15 +0200
Subject: [PATCH 09/13] lavc/jpeg2000: Speed up ff_jpeg2000_tag_tree_init()
 using stereotypes for sizes <= 4x4

---
 libavcodec/jpeg2000.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/libavcodec/jpeg2000.c b/libavcodec/jpeg2000.c
index 0bec2e187d..b80e68bcba 100644
--- a/libavcodec/jpeg2000.c
+++ b/libavcodec/jpeg2000.c
@@ -51,6 +51,31 @@  static int32_t tag_tree_size(int w, int h)
     return (int32_t)(res + 1);
 }
 
+#define T(x) (x*sizeof(Jpeg2000TgtNode))
+
+static const size_t tt_sizes[16] = {
+    T(1),T(3),T(6),T(7),T(3),T(5),T(9),T(11),T(6),T(9),T(14),T(17),T(7),T(11),T(17),T(21),
+};
+
+static const Jpeg2000TgtNode tt_stereotypes[16][21] = {
+    {{-1},},
+    {{2},{2},{-1},},
+    {{3},{3},{4},{5},{5},{-1},},
+    {{4},{4},{5},{5},{6},{6},{-1},},
+    {{2},{2},{-1},},
+    {{4},{4},{4},{4},{-1},},
+    {{6},{6},{7},{6},{6},{7},{8},{8},{-1},},
+    {{8},{8},{9},{9},{8},{8},{9},{9},{10},{10},{-1},},
+    {{3},{3},{4},{5},{5},{-1},},
+    {{6},{6},{6},{6},{7},{7},{8},{8},{-1},},
+    {{9},{9},{10},{9},{9},{10},{11},{11},{12},{13},{13},{13},{13},{-1},},
+    {{12},{12},{13},{13},{12},{12},{13},{13},{14},{14},{15},{15},{16},{16},{16},{16},{-1},},
+    {{4},{4},{5},{5},{6},{6},{-1},},
+    {{8},{8},{8},{8},{9},{9},{9},{9},{10},{10},{-1},},
+    {{12},{12},{13},{12},{12},{13},{14},{14},{15},{14},{14},{15},{16},{16},{16},{16},{-1},},
+    {{16},{16},{17},{17},{16},{16},{17},{17},{18},{18},{19},{19},{18},{18},{19},{19},{20},{20},{20},{20},{-1},},
+};
+
 /* allocate the memory for tag tree */
 static int ff_jpeg2000_tag_tree_init(Jpeg2000TgtNode **old, unsigned int *size, int w, int h)
 {
@@ -59,6 +84,15 @@  static int ff_jpeg2000_tag_tree_init(Jpeg2000TgtNode **old, unsigned int *size,
     int32_t tt_size, ofs = 0;
     size_t prod;
 
+    if (w <= 4 && h <= 4) {
+        int idx = w-1 + (h-1)*4;
+        size_t sz = tt_sizes[idx];
+        av_fast_malloc(old, size, sz);
+        if (*old) {
+            memcpy(*old, tt_stereotypes[idx], sz);
+        }
+        return 0;
+    } else {
     tt_size = tag_tree_size(w, h);
 
     if (av_size_mult(tt_size, sizeof(*t), &prod))
@@ -87,6 +121,7 @@  static int ff_jpeg2000_tag_tree_init(Jpeg2000TgtNode **old, unsigned int *size,
     }
     t[0].parent = -1;
     return 0;
+    }
 }
 
 void ff_tag_tree_zero(Jpeg2000TgtNode *t, int w, int h, int val)
-- 
2.30.2